| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 11.0, | |
| "global_step": 12914, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9914821124361162e-05, | |
| "loss": 4.8491, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 4.696099281311035, | |
| "eval_runtime": 907.3534, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.982964224872232e-05, | |
| "loss": 4.88, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 4.71148681640625, | |
| "eval_runtime": 901.0601, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.9744463373083477e-05, | |
| "loss": 4.6409, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 4.671314239501953, | |
| "eval_runtime": 906.18, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.9659284497444635e-05, | |
| "loss": 4.7222, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 4.637036323547363, | |
| "eval_runtime": 903.4161, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.9574105621805795e-05, | |
| "loss": 4.6357, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 4.6376471519470215, | |
| "eval_runtime": 912.9746, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.9488926746166953e-05, | |
| "loss": 4.6993, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 4.662974834442139, | |
| "eval_runtime": 908.9893, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.940374787052811e-05, | |
| "loss": 4.7104, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 4.587018966674805, | |
| "eval_runtime": 913.6781, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.04, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.9318568994889268e-05, | |
| "loss": 4.5864, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 4.565457344055176, | |
| "eval_runtime": 900.1349, | |
| "eval_samples_per_second": 0.326, | |
| "eval_steps_per_second": 0.041, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.923339011925043e-05, | |
| "loss": 4.6003, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 4.560632705688477, | |
| "eval_runtime": 913.1928, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.9148211243611586e-05, | |
| "loss": 4.6166, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 4.5305914878845215, | |
| "eval_runtime": 898.0505, | |
| "eval_samples_per_second": 0.326, | |
| "eval_steps_per_second": 0.041, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.9063032367972743e-05, | |
| "loss": 4.6019, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 4.547730922698975, | |
| "eval_runtime": 916.6743, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.89778534923339e-05, | |
| "loss": 4.4833, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 4.527022838592529, | |
| "eval_runtime": 905.1447, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.889267461669506e-05, | |
| "loss": 4.4664, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 4.533600807189941, | |
| "eval_runtime": 900.1154, | |
| "eval_samples_per_second": 0.326, | |
| "eval_steps_per_second": 0.041, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.880749574105622e-05, | |
| "loss": 4.4533, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 4.512392044067383, | |
| "eval_runtime": 897.9913, | |
| "eval_samples_per_second": 0.326, | |
| "eval_steps_per_second": 0.041, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.872231686541738e-05, | |
| "loss": 4.2969, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 4.5288238525390625, | |
| "eval_runtime": 902.8396, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.8637137989778534e-05, | |
| "loss": 4.4203, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 4.510149002075195, | |
| "eval_runtime": 896.5776, | |
| "eval_samples_per_second": 0.327, | |
| "eval_steps_per_second": 0.041, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.8551959114139694e-05, | |
| "loss": 4.4828, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 4.4747633934021, | |
| "eval_runtime": 900.0595, | |
| "eval_samples_per_second": 0.326, | |
| "eval_steps_per_second": 0.041, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.8466780238500855e-05, | |
| "loss": 4.5045, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 4.477636337280273, | |
| "eval_runtime": 930.3322, | |
| "eval_samples_per_second": 0.315, | |
| "eval_steps_per_second": 0.04, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.8381601362862013e-05, | |
| "loss": 4.2977, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 4.475375175476074, | |
| "eval_runtime": 897.0451, | |
| "eval_samples_per_second": 0.327, | |
| "eval_steps_per_second": 0.041, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.829642248722317e-05, | |
| "loss": 4.4022, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 4.451622486114502, | |
| "eval_runtime": 924.228, | |
| "eval_samples_per_second": 0.317, | |
| "eval_steps_per_second": 0.04, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.8211243611584328e-05, | |
| "loss": 4.3429, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 4.43123722076416, | |
| "eval_runtime": 903.4516, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.812606473594549e-05, | |
| "loss": 4.3748, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 4.475191116333008, | |
| "eval_runtime": 901.3458, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.8040885860306646e-05, | |
| "loss": 4.343, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 4.455069541931152, | |
| "eval_runtime": 919.5227, | |
| "eval_samples_per_second": 0.319, | |
| "eval_steps_per_second": 0.04, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.7955706984667803e-05, | |
| "loss": 4.1796, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 4.424516201019287, | |
| "eval_runtime": 912.0297, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.787052810902896e-05, | |
| "loss": 4.2325, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 4.425054550170898, | |
| "eval_runtime": 900.4656, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.778534923339012e-05, | |
| "loss": 4.2419, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 4.426344871520996, | |
| "eval_runtime": 907.7136, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.770017035775128e-05, | |
| "loss": 4.2556, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_loss": 4.392487525939941, | |
| "eval_runtime": 904.6208, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.761499148211244e-05, | |
| "loss": 4.2501, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 4.414584636688232, | |
| "eval_runtime": 904.1877, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 1.7529812606473594e-05, | |
| "loss": 4.2199, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 4.391025543212891, | |
| "eval_runtime": 904.8782, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.7444633730834754e-05, | |
| "loss": 4.1842, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 4.3928704261779785, | |
| "eval_runtime": 911.7639, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.7359454855195912e-05, | |
| "loss": 4.1789, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 4.373032569885254, | |
| "eval_runtime": 903.6693, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.7274275979557073e-05, | |
| "loss": 4.1993, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 4.401707172393799, | |
| "eval_runtime": 906.6931, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.718909710391823e-05, | |
| "loss": 4.1348, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 4.366961479187012, | |
| "eval_runtime": 909.5878, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.7103918228279387e-05, | |
| "loss": 4.196, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 4.354998588562012, | |
| "eval_runtime": 914.5578, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.7018739352640548e-05, | |
| "loss": 4.1906, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 4.349732875823975, | |
| "eval_runtime": 898.3438, | |
| "eval_samples_per_second": 0.326, | |
| "eval_steps_per_second": 0.041, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.6933560477001706e-05, | |
| "loss": 4.0583, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_loss": 4.3627471923828125, | |
| "eval_runtime": 897.909, | |
| "eval_samples_per_second": 0.326, | |
| "eval_steps_per_second": 0.041, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.6848381601362863e-05, | |
| "loss": 4.1298, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_loss": 4.362400531768799, | |
| "eval_runtime": 912.2819, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 1.676320272572402e-05, | |
| "loss": 4.0244, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_loss": 4.338736534118652, | |
| "eval_runtime": 896.0396, | |
| "eval_samples_per_second": 0.327, | |
| "eval_steps_per_second": 0.041, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.667802385008518e-05, | |
| "loss": 4.0549, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "eval_loss": 4.341971397399902, | |
| "eval_runtime": 901.737, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.659284497444634e-05, | |
| "loss": 4.0006, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_loss": 4.326377868652344, | |
| "eval_runtime": 898.1346, | |
| "eval_samples_per_second": 0.326, | |
| "eval_steps_per_second": 0.041, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 1.65076660988075e-05, | |
| "loss": 4.0435, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "eval_loss": 4.331975936889648, | |
| "eval_runtime": 901.1995, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.6422487223168653e-05, | |
| "loss": 4.0948, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "eval_loss": 4.32388973236084, | |
| "eval_runtime": 904.6488, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.6337308347529814e-05, | |
| "loss": 3.933, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "eval_loss": 4.314174175262451, | |
| "eval_runtime": 902.3829, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.625212947189097e-05, | |
| "loss": 3.9773, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 4.353682041168213, | |
| "eval_runtime": 901.0754, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1.6166950596252132e-05, | |
| "loss": 4.1143, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_loss": 4.3104963302612305, | |
| "eval_runtime": 903.7164, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 1.608177172061329e-05, | |
| "loss": 3.961, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 4.292612552642822, | |
| "eval_runtime": 900.6329, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.5996592844974447e-05, | |
| "loss": 4.0047, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 4.3063883781433105, | |
| "eval_runtime": 900.2789, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1.5911413969335605e-05, | |
| "loss": 3.9058, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 4.303318023681641, | |
| "eval_runtime": 906.0598, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 1.5826235093696765e-05, | |
| "loss": 3.7936, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "eval_loss": 4.301506996154785, | |
| "eval_runtime": 906.1238, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 1.5741056218057923e-05, | |
| "loss": 3.8733, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_loss": 4.344919681549072, | |
| "eval_runtime": 916.0111, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 1.565587734241908e-05, | |
| "loss": 3.8625, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "eval_loss": 4.274160385131836, | |
| "eval_runtime": 906.5215, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 1.557069846678024e-05, | |
| "loss": 4.0015, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_loss": 4.2957258224487305, | |
| "eval_runtime": 920.9763, | |
| "eval_samples_per_second": 0.318, | |
| "eval_steps_per_second": 0.04, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 1.54855195911414e-05, | |
| "loss": 4.0173, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "eval_loss": 4.30204439163208, | |
| "eval_runtime": 900.2302, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 1.5400340715502556e-05, | |
| "loss": 3.8079, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_loss": 4.274052619934082, | |
| "eval_runtime": 902.0347, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 1.5315161839863713e-05, | |
| "loss": 4.0081, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "eval_loss": 4.2950968742370605, | |
| "eval_runtime": 910.5366, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 1.5229982964224874e-05, | |
| "loss": 3.8823, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "eval_loss": 4.277224540710449, | |
| "eval_runtime": 901.0907, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 1.5144804088586031e-05, | |
| "loss": 3.9056, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_loss": 4.272303581237793, | |
| "eval_runtime": 911.2022, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 1.505962521294719e-05, | |
| "loss": 3.813, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_loss": 4.275490760803223, | |
| "eval_runtime": 913.2487, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1.4974446337308348e-05, | |
| "loss": 3.9263, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "eval_loss": 4.2567267417907715, | |
| "eval_runtime": 922.3278, | |
| "eval_samples_per_second": 0.318, | |
| "eval_steps_per_second": 0.04, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 1.4889267461669507e-05, | |
| "loss": 3.7405, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "eval_loss": 4.279594421386719, | |
| "eval_runtime": 902.112, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 1.4804088586030664e-05, | |
| "loss": 3.8432, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "eval_loss": 4.277362823486328, | |
| "eval_runtime": 909.7644, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 1.4718909710391824e-05, | |
| "loss": 3.797, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "eval_loss": 4.2573161125183105, | |
| "eval_runtime": 900.2164, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 1.4633730834752981e-05, | |
| "loss": 3.7348, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "eval_loss": 4.261054515838623, | |
| "eval_runtime": 899.5894, | |
| "eval_samples_per_second": 0.326, | |
| "eval_steps_per_second": 0.041, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 1.4548551959114142e-05, | |
| "loss": 3.7363, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "eval_loss": 4.2909698486328125, | |
| "eval_runtime": 914.0387, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.04, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 1.44633730834753e-05, | |
| "loss": 3.8448, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "eval_loss": 4.257021903991699, | |
| "eval_runtime": 906.6331, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 1.4378194207836458e-05, | |
| "loss": 3.8023, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "eval_loss": 4.263571262359619, | |
| "eval_runtime": 903.3527, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 1.4293015332197616e-05, | |
| "loss": 3.8202, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "eval_loss": 4.226749897003174, | |
| "eval_runtime": 913.4737, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 1.4207836456558775e-05, | |
| "loss": 3.731, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_loss": 4.232919216156006, | |
| "eval_runtime": 905.4134, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 1.4122657580919934e-05, | |
| "loss": 3.7507, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "eval_loss": 4.2412004470825195, | |
| "eval_runtime": 917.4159, | |
| "eval_samples_per_second": 0.319, | |
| "eval_steps_per_second": 0.04, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 1.4037478705281091e-05, | |
| "loss": 3.8812, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_loss": 4.239901542663574, | |
| "eval_runtime": 904.0296, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.395229982964225e-05, | |
| "loss": 3.6882, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "eval_loss": 4.252227306365967, | |
| "eval_runtime": 909.685, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 1.3867120954003408e-05, | |
| "loss": 3.6485, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 4.240085601806641, | |
| "eval_runtime": 917.8845, | |
| "eval_samples_per_second": 0.319, | |
| "eval_steps_per_second": 0.04, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 1.3781942078364567e-05, | |
| "loss": 3.6561, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "eval_loss": 4.261867046356201, | |
| "eval_runtime": 912.6991, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 1.3696763202725724e-05, | |
| "loss": 3.6851, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "eval_loss": 4.274002552032471, | |
| "eval_runtime": 911.5799, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1.3611584327086883e-05, | |
| "loss": 3.7842, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "eval_loss": 4.243954658508301, | |
| "eval_runtime": 906.9325, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 1.352640545144804e-05, | |
| "loss": 3.6484, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_loss": 4.238761901855469, | |
| "eval_runtime": 910.5622, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 1.3441226575809202e-05, | |
| "loss": 3.7509, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_loss": 4.240095138549805, | |
| "eval_runtime": 935.7714, | |
| "eval_samples_per_second": 0.313, | |
| "eval_steps_per_second": 0.04, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 1.3356047700170357e-05, | |
| "loss": 3.7597, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "eval_loss": 4.256958484649658, | |
| "eval_runtime": 915.2208, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 1.3270868824531518e-05, | |
| "loss": 3.7253, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "eval_loss": 4.291894435882568, | |
| "eval_runtime": 915.8862, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 1.3185689948892676e-05, | |
| "loss": 3.7335, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "eval_loss": 4.206986427307129, | |
| "eval_runtime": 916.8897, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 1.3100511073253835e-05, | |
| "loss": 3.6213, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_loss": 4.203628063201904, | |
| "eval_runtime": 910.5741, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 1.3015332197614992e-05, | |
| "loss": 3.588, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_loss": 4.219061851501465, | |
| "eval_runtime": 910.3103, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 1.2930153321976151e-05, | |
| "loss": 3.6381, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "eval_loss": 4.232492923736572, | |
| "eval_runtime": 903.8691, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 1.284497444633731e-05, | |
| "loss": 3.6023, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "eval_loss": 4.247186183929443, | |
| "eval_runtime": 910.7714, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 1.2759795570698468e-05, | |
| "loss": 3.5601, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "eval_loss": 4.2428107261657715, | |
| "eval_runtime": 926.441, | |
| "eval_samples_per_second": 0.316, | |
| "eval_steps_per_second": 0.04, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 1.2674616695059627e-05, | |
| "loss": 3.6893, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "eval_loss": 4.235583305358887, | |
| "eval_runtime": 905.7471, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 1.2589437819420784e-05, | |
| "loss": 3.4977, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "eval_loss": 4.210697650909424, | |
| "eval_runtime": 909.4116, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 1.2504258943781943e-05, | |
| "loss": 3.5489, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "eval_loss": 4.2333455085754395, | |
| "eval_runtime": 899.4646, | |
| "eval_samples_per_second": 0.326, | |
| "eval_steps_per_second": 0.041, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 1.24190800681431e-05, | |
| "loss": 3.5786, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "eval_loss": 4.2256317138671875, | |
| "eval_runtime": 907.6718, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 1.2333901192504261e-05, | |
| "loss": 3.5991, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "eval_loss": 4.206646919250488, | |
| "eval_runtime": 928.2897, | |
| "eval_samples_per_second": 0.316, | |
| "eval_steps_per_second": 0.04, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 1.2248722316865417e-05, | |
| "loss": 3.6571, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "eval_loss": 4.213482856750488, | |
| "eval_runtime": 913.2222, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1.2163543441226578e-05, | |
| "loss": 3.5465, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "eval_loss": 4.197275638580322, | |
| "eval_runtime": 906.8727, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 1.2078364565587735e-05, | |
| "loss": 3.6476, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "eval_loss": 4.191103935241699, | |
| "eval_runtime": 910.3991, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 1.1993185689948894e-05, | |
| "loss": 3.6669, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "eval_loss": 4.2001953125, | |
| "eval_runtime": 908.1025, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 1.1908006814310052e-05, | |
| "loss": 3.4399, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "eval_loss": 4.230240345001221, | |
| "eval_runtime": 914.9264, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 1.1822827938671211e-05, | |
| "loss": 3.5381, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "eval_loss": 4.2084150314331055, | |
| "eval_runtime": 928.1244, | |
| "eval_samples_per_second": 0.316, | |
| "eval_steps_per_second": 0.04, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 1.1737649063032368e-05, | |
| "loss": 3.5008, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "eval_loss": 4.216128826141357, | |
| "eval_runtime": 913.9443, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.04, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 1.1652470187393527e-05, | |
| "loss": 3.6199, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "eval_loss": 4.218649387359619, | |
| "eval_runtime": 916.6151, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 1.1567291311754685e-05, | |
| "loss": 3.5997, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "eval_loss": 4.269123554229736, | |
| "eval_runtime": 902.9645, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 1.1482112436115844e-05, | |
| "loss": 3.5075, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "eval_loss": 4.2026848793029785, | |
| "eval_runtime": 903.7139, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 1.1396933560477003e-05, | |
| "loss": 3.5163, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "eval_loss": 4.2565717697143555, | |
| "eval_runtime": 909.1873, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 1.131175468483816e-05, | |
| "loss": 3.4902, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "eval_loss": 4.208179473876953, | |
| "eval_runtime": 901.8843, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 1.1226575809199321e-05, | |
| "loss": 3.4829, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "eval_loss": 4.217052459716797, | |
| "eval_runtime": 913.5755, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 1.1141396933560477e-05, | |
| "loss": 3.599, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_loss": 4.216422080993652, | |
| "eval_runtime": 904.6206, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 1.1056218057921638e-05, | |
| "loss": 3.5058, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "eval_loss": 4.200262069702148, | |
| "eval_runtime": 908.4763, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 1.0971039182282795e-05, | |
| "loss": 3.4622, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "eval_loss": 4.201136112213135, | |
| "eval_runtime": 918.5088, | |
| "eval_samples_per_second": 0.319, | |
| "eval_steps_per_second": 0.04, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 1.0885860306643954e-05, | |
| "loss": 3.4836, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "eval_loss": 4.196112632751465, | |
| "eval_runtime": 907.3086, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 1.0800681431005112e-05, | |
| "loss": 3.4177, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "eval_loss": 4.2310028076171875, | |
| "eval_runtime": 904.8795, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 1.071550255536627e-05, | |
| "loss": 3.4407, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "eval_loss": 4.2216362953186035, | |
| "eval_runtime": 910.613, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 1.0630323679727428e-05, | |
| "loss": 3.44, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "eval_loss": 4.2364935874938965, | |
| "eval_runtime": 907.4387, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 1.0545144804088587e-05, | |
| "loss": 3.5116, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "eval_loss": 4.201255798339844, | |
| "eval_runtime": 905.3716, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 1.0459965928449745e-05, | |
| "loss": 3.4793, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "eval_loss": 4.203760147094727, | |
| "eval_runtime": 903.5367, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 1.0374787052810904e-05, | |
| "loss": 3.4414, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "eval_loss": 4.177506923675537, | |
| "eval_runtime": 904.4055, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 1.0289608177172061e-05, | |
| "loss": 3.509, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "eval_loss": 4.204129695892334, | |
| "eval_runtime": 904.4565, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 1.020442930153322e-05, | |
| "loss": 3.464, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "eval_loss": 4.2182393074035645, | |
| "eval_runtime": 915.8218, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 1.0119250425894378e-05, | |
| "loss": 3.3574, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "eval_loss": 4.222841262817383, | |
| "eval_runtime": 916.715, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 1.0034071550255537e-05, | |
| "loss": 3.4134, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "eval_loss": 4.198949813842773, | |
| "eval_runtime": 911.1975, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 9.948892674616696e-06, | |
| "loss": 3.4876, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "eval_loss": 4.1779093742370605, | |
| "eval_runtime": 905.3949, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 9.863713798977853e-06, | |
| "loss": 3.3188, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "eval_loss": 4.199155330657959, | |
| "eval_runtime": 906.4403, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 9.778534923339012e-06, | |
| "loss": 3.4336, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "eval_loss": 4.215114593505859, | |
| "eval_runtime": 918.8261, | |
| "eval_samples_per_second": 0.319, | |
| "eval_steps_per_second": 0.04, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "learning_rate": 9.693356047700172e-06, | |
| "loss": 3.3774, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "eval_loss": 4.194676876068115, | |
| "eval_runtime": 912.8562, | |
| "eval_samples_per_second": 0.321, | |
| "eval_steps_per_second": 0.041, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "learning_rate": 9.608177172061329e-06, | |
| "loss": 3.2942, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "eval_loss": 4.212912082672119, | |
| "eval_runtime": 905.2405, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 9.522998296422488e-06, | |
| "loss": 3.4431, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "eval_loss": 4.1929144859313965, | |
| "eval_runtime": 908.9828, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 9.437819420783645e-06, | |
| "loss": 3.3895, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "eval_loss": 4.221463203430176, | |
| "eval_runtime": 905.8419, | |
| "eval_samples_per_second": 0.323, | |
| "eval_steps_per_second": 0.041, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 9.352640545144805e-06, | |
| "loss": 3.4624, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "eval_loss": 4.192135334014893, | |
| "eval_runtime": 915.7075, | |
| "eval_samples_per_second": 0.32, | |
| "eval_steps_per_second": 0.04, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 9.267461669505964e-06, | |
| "loss": 3.3823, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "eval_loss": 4.197402477264404, | |
| "eval_runtime": 902.8153, | |
| "eval_samples_per_second": 0.325, | |
| "eval_steps_per_second": 0.041, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 9.182282793867123e-06, | |
| "loss": 3.3671, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "eval_loss": 4.152112007141113, | |
| "eval_runtime": 903.9495, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 9.09710391822828e-06, | |
| "loss": 3.2883, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "eval_loss": 4.178409576416016, | |
| "eval_runtime": 904.0493, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 9.01192504258944e-06, | |
| "loss": 3.4145, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_loss": 4.208373546600342, | |
| "eval_runtime": 903.9191, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 12900 | |
| } | |
| ], | |
| "max_steps": 23480, | |
| "num_train_epochs": 20, | |
| "total_flos": 4.542855419394294e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |